© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1261
    Prev
    Next
    INDEX
    Explanations

    terminology specific to scientific and technical studies, particularly those with lab components.

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.59
    TagMode
    -0.56
    MessageTagHelper
    -0.54
    ConstraintMaker
    -0.53
    tonode
    -0.52
    dataclass
    -0.51
     Italijani
    -0.50
    InputTagHelper
    -0.49
    XmlRootElement
    -0.49
    plash
    -0.48
    POSITIVE LOGITS
    مصادر
    0.57
    Kaynakça
    0.54
    ongo
    0.50
     jöv
    0.50
     NOS
    0.50
     cref
    0.49
     tiên
    0.48
    NameInMap
    0.48
    zco
    0.48
    ########.
    0.47
    Activations Density 10.668%

    No Known Activations